检索结果-内蒙古大学图书馆

2025 International Conference on Electrical automation and Artificial intelligence, ICEAAI 2025

作者： Zhang, Kunsan Zhang, Song Pan, Siqi Lin, Jinhuang State Grid Fujian Electric Power Co. Ltd. Zhangzhou Power Supply Company Zhangzhou China

ISBN: (纸本)9798331506797

With the rapid advancement of artificial intelligence, particularly deep learning, intrusion detection methods based on deep learning have gained significant attention. Deep learning can automatically extract features from large datasets and classify complex patterns, offering better adaptability and flexibility than traditional methods. It is especially effective in handling dynamic industrial environments and unknown attacks, improving detection accuracy while reducing false positives and false negatives. However, challenges remain, such as model generalization and computational efficiency. To address these, this paper proposes an improved triplet neural network-based intrusion detection method for industrial control systems (ICS). The system includes modules for data collection, preprocessing, model construction, training, and real-time detection. By incorporating a self-attention mechanism, the improved model better recognizes complex attack patterns and adapts to new threats. Experimental results show an accuracy of 98.7%, with a significant reduction in false positives and false negatives, enhancing ICS security and providing a new approach for handling future cyberattacks. © 2025 ieee.

关键词： Deep Learning Industrial control Systems (ICS) Intrusion Detection

来源：评论

学校读者我要写书评

暂无评论

Comparison of optimization algorithms for installation error calibration of accelerometer arrays

Comparison of optimization algorithms for installation error...

引用

International symposium on computational intelligence and Informatics

作者： Richard Pesti Peter Sarcevic Dominik Csík Istvan Nagy Akos Odry Doctoral School of Applied Informatics and Applied Mathematics Óbuda University Budapest Hungary Department of Mechatronics and Automation University of Szeged Szeged Hungary Bánki Donát Faculty of Mechanical and Safety Engineering Óbuda University Budapest Hungary

Accelerometers play a crucial role in localization problems, but their accuracy depends on the precision of the calibration process. In this paper, a comparison of optimization algorithms is presented within the scope of between sensor error calibration. The Particle Swarm optimization (PSO) and Genetic Algorithm (GA) are proposed for the problem, and tested in three different setups. Moreover, the MATLAB built-in fmincon minimization algorithm is also evaluated for calibration parameter estimation. A custom fitness function is proposed to obtain the between sensor misalignment and bias errors, for two accelerometers. The analysis highlights that the algorithms can successfully determine the between sensor error parameters. The conducted comparison shows that fmincon reached an outstanding speed in terms of convergency, but in overall PSO has produced better results compared to GA and fmincon. PSO is more suitable for the calibration problem because of its robustness and stability characteristics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Safe trajectory design for indoor drones using reinforcement-learning-based methods

Safe trajectory design for indoor drones using reinforcement...

引用

International symposium on Applied computational intelligence and Informatics ( SACI)

作者： Dénes Tompos Balázs Németh Eötvös Loránd Research Network (ELKH) Kende utca 13-17. Institute for Computer Science and Control (SZTAKI) Budapest Hungary Department of Control for Transportation and Vehicle Systems Budapest University of Technology and Economics Stoczek u. 2. Budapest Hungary

This paper proposes a design method for achieving safe trajectory of indoor drones. The trajectory design with a reinforcement-learning-based (RL) agent is facilitated, which can result in efficient and collision-free motion. The method is developed for motion in indoor area with moving mobile robots, and thus, the collision with these obstacles must be avoided. Through RL-based design the fast motion of the drones can be achieved, which must perform a mission between workstations in a manufacturing system. The effectiveness of the design process through a simulation example on a real laboratory environment is illustrated.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI Threat Detection and Response on Smart Networks 13th

AI Threat Detection and Response on Smart Networks

引用

13th International Conference on computational Collective intelligence (ICCCI)

作者： Dermetzis, Konstantinos Iliadis, Lazaros Democritus Univ Thrace Sch Civil Engn Xanthi Greece Int Hellenic Univ Dept Phys Kavala Greece

ISBN: (纸本)9783030880811;9783030880804

The main goal of smart cities is to dynamically optimize the quality of life, through the application of information and communication technologies (ICT). The involved networks, require a continuous increase in data exchange, in order to intelligently control services and in particular, mechanisms that activate a higher degree of automation in the city. As many critical services are interconnected, the need for cyber security is increasing, in order to ensure data exchange protection, privacy, and better health and safety services for all citizens. The security and evolution of smart cities is based on the security of their smart networks which are activated by specific automation mechanisms, such as the SCADA networks and the pre-eminent automation systems. This paper presents the AnomaTS, an advanced Machine Learning system, for anomaly detection in sensors of SCADA networks, taking into account the temporal state of their mechanisms.

关键词： Smart city AI Anomaly detection Cyber threat computational intelligence SCADA

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Benchmark for Autonomous Driving in Intersection Scenarios

A Reinforcement Learning Benchmark for Autonomous Driving in...

引用

ieee symposium Series on computational intelligence (ieee SSCI)

作者： Liu, Yuqi Zhang, Qichao Zhao, Dongbin Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China

ISBN: (纸本)9781728190488

In recent years, control under urban intersection scenarios has become an emerging research topic. In such scenarios, the autonomous vehicle confronts complicated situations since it must deal with the interaction with social vehicles timely while obeying the traffic rules. Generally, the autonomous vehicle is supposed to avoid collisions while pursuing better efficiency. The existing work fails to provide a framework that emphasizes the integrity of the scenarios while deploying and testing reinforcement learning(RL) methods. Specifically, we propose a benchmark for training and testing RL-based autonomous driving agents in complex intersection scenarios, which is called RL-CIS. Then, a set of baselines consisting various algorithms are deployed. The test benchmark and baselines provide a fair and comprehensive training and testing platform for the study of RL for autonomous driving in the intersection scenario, advancing RL-based methods for autonomous driving control. The code of our proposed framework can be found at https://***/liuyuqi123/ComplexUrbanScenarios.

关键词： autonomous driving reinforcement learning intersection scenarios decision-making

来源：评论

学校读者我要写书评

暂无评论

A Constrained Path Following Method for Snake-like Manipulators via controlled Winding Uncoiling Strategy

A Constrained Path Following Method for Snake-like Manipulat...

引用

ieee International Conference on Robotics and automation (ICRA)

作者： Mingrui Luo Yunong Tian Yinghua Cao Minghao Chen Yanfeng Zhang En Li Min Tan Chinese Academy of Sciences Engineering Laboratory of Industrial Vision and Intelligent Equipment Technology Institute of Automation Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Benefiting from its hyper-redundant structure, the biomimetic snake-like manipulator retains its remarkable flexibility even within confined spaces. However, its motion planning and control pose significant challenges. This paper imitates the winding uncoiling behavior of snakes to achieve controllable constrained path following. Firstly, based on control points, a recursive computational model and an equivalent planning angle model are established, enabling efficient and analytical determination of joint positions, collision regions, and motion parameters during the path following. Subsequently, the sliding control point algorithm and motion smoothing restriction algorithm are designed. The former ensures that the remaining segments during following strictly remain within the collision-free regions defined by the base and path controls, while the latter smooths the control parameters based on velocity and acceleration limitations. Finally, simulation and practical experiments demonstrate the feasibility of the proposed methods. The prototype that applied our method can reach targets and accomplish tasks, further validating the applicability of the snake-like manipulator.

关键词： Analytical models Smoothing methods computational modeling Biological system modeling Windings Prototypes Manipulators

来源：评论

学校读者我要写书评

暂无评论

Fourier U-Shaped Network for Multi-Variate Time Series Forecasting

Fourier U-Shaped Network for Multi-Variate Time Series Forec...

引用

ieee symposium Series on computational intelligence (SSCI)

作者： Baowen Xu Xuelei Wang Chengbao Liu Shuo Li Chinese Academy of Sciences Institute of Automation Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Multi-variate time series forecasting plays a crucial role in addressing key tasks across various domains, such as early warning, pre-planning, resource scheduling, and other critical tasks. Thus, accurate multi-variate time series forecasting is of significant importance in guiding practical applications and facilitating these essential tasks. Recently, Transformer-based multi-variate time series forecasting models have demonstrated tremendous potential due to their outstanding performance in long-term time predictions. However, Transformer-based models for multi-variate time series forecasting often come with high time complexity and computational costs. Therefore, we propose a low time complexity model called Fourier U-shaped Network (F-UNet) for multi-variate time series forecasting, which is non-Transformer based. Specifically, F-UNet is composed of low time complexity neural network components, such as Fourier neural operator and feed-forward neural network, arranged in a U-shaped architecture. F-UNet conducts channel and temporal modeling separately for the multi-variate time series. The U-Net constructed based on Fourier neural operators is employed to achieve channel interactions, while linear layers are used to realize temporal interactions. Experimental results on several real-world datasets demonstrate that F-UNet outperforms existing Transformer-based models with higher efficiency in multi-variate time series forecasting.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Meta Learning With Paired Forward and Inverse Models for Efficient Receding Horizon control

引用

ieee ROBOTICS AND automation LETTERS 2021年第2期6卷 3240-3247页

作者： McKinnon, Christopher Schoellig, Angela P. Univ Toronto Dynam Syst Lab Inst Aerosp Studies Toronto ON M3H 5T6 Canada Vector Inst Artificial Intelligence Toronto ON M3H 5T6 Canada

This paper presents a model-learning method for Stochastic Model Predictive control (SMPC) that is both accurate and computationally efficient. We assume that the control input affects the robot dynamics through an unknown (but invertable) nonlinear function. By learning this unknown function and its inverse, we can use the value of the function as a new control input (which we call the input feature) that is optimised by SMPC in place of the original control input. This removes the need to evaluate a function approximator for the unknown function during optimisation in SMPC (where it would be evaluated many times), reducing the computational cost. The learned inverse is evaluated only once at each sampling time to convert the optimal input feature from SMPC to a control input to apply to the system. We assume that the remaining unknown dynamics can be accurately represented as a model that is linear in a set of coefficients, which enables fast adaptation to new conditions. We demonstrate our approach in experiments on a large ground robot using a stereo camera for localisation.

关键词： Field robots model learning for control robust adaptive control

来源：评论

学校读者我要写书评

暂无评论

On Modifications Towards Improvement of the Exploitation Phase for SOMA Algorithm with Clustering-aided Migration and Adaptive Perturbation Vector control

On Modifications Towards Improvement of the Exploitation Pha...

引用

ieee symposium Series on computational intelligence (ieee SSCI)

作者： Kadavy, Tomas Viktorin, Adam Pluhacek, Michal Kovar, Stanislav Tomas Bata Univ Zlin Fac Appl Informat Zlin Czech Republic

ISBN: (纸本)9781728190488

This paper represents the next step in the development of the recently proposed single objective metaheuristic algorithm - Self-Organizing Migrating Algorithm with CLustering-aided migration and adaptive Perturbation vector control (SOMA-CLP). The CEC 2021 single objective bound-constrained optimization benchmark testbed was used for the performance evaluation of the modifications of the algorithm. The presented modifications were invoked by the results of CEC 2021 competition, where the SOMA-CLP ranked 7th out of 9 competing algorithms. This paper introduces three modifications of population organization process focusing on one particular phase of the SOMA-CLP algorithm aimed at exploitation. All results were compared and tested for statistical significance against the original variant using the Friedman rank test. The algorithm modification and analysis of the results presented here can be inspiring for other researchers working on the development and modifications of evolutionary computing techniques.

关键词： SOMA SOMA-CLP k-means clustering benchmarking CEC 2021 population dynamics

来源：评论

学校读者我要写书评

暂无评论

Model predictive fuzzy control in chemotherapy optimization

Model predictive fuzzy control in chemotherapy optimization

引用

International symposium on Applied computational intelligence and Informatics ( SACI)

作者： Tamás Dániel Szűcs Melánia Puskás Dániel András Drexler Levente Kovács Physiological Controls Research Center Research and Innovation Center of Óbuda University Óbuda University Budapest Hungary

Nowadays clinical therapies in chemotherapy sessions are generalized for patients, therefore we are working to provide a personalized drug plan to help reduce the drug dosage, causing the reduction of side effects and costs. Also, one benefit of this method is to prevent drug resistance. In order to improve the efficiency of the in vivo experiments, mathematical optimization is needed. We implemented a chemotherapeutical drug dosing algorithm based on a fuzzy logic search that is providing an initial value for a model predictive control system that calculates the minimum dose using a linear quadratic fitness function. This results in a suboptimal drug dose therapy plan. These results seem satisfactory in order to replace the traditional chemotherapy plans in the nearby future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：